Abstract
Undergraduate thesis as the final project, or in Indonesian called as Tugas Akhir, for each undergraduate student is a pre-requisite before student graduation and the successfulness in finishing the project becomes as one of learning outcomes among others. Determining the topic of the final project according to the ability of students is an important thing. One strategy to decide the topic is reading some literatures but it takes up more time. There is a need for a recommendation system to help students in determining the topic according to their abilities or subject understanding which is based on their academic transcripts. This study focused on a system for final project topic recommendations based on evaluating competencies in previous academic transcripts of graduated students. Collected data of previous final projects, namely titles and abstracts weighted by term occurences of TF-IDF (term frequency–inverse document frequency) and grouped by using K-Means Clustering. From each cluster result, we prepared candidates for recommended topics using Latent Dirichlet Allocation (LDA) with Gibbs Sampling that focusing on the word distribution of each topic in the cluster. Some evaluations were performed to evaluate the optimal cluster number, topic number and then made more thorough exploration on the recommendation results. Our experiments showed that the proposed system could recommend final project topic ideas based on student competence represented in their academic transcripts.
Highlights
Undergraduate thesis as the final project, or in Indonesian called as Tugas Akhir, for each undergraduate student is a prerequisite before student graduation and the successfulness in finishing the project becomes as one of learning outcomes among others
There is a need for a recommendation system to help students in determining the topic according to their abilities or subject understanding which is based on their academic transcripts
This study focused on a system for final project topic recommendations based on evaluating competencies in previous academic transcripts of graduated students
Summary
Tugas akhir merupakan prasayarat kelulusan untuk memenuhi target capaian pembelajaran program sarjana di perguruan tinggi [1] agar seorang mahasiswa mampu mengaplikasikan pengetahuan, keterampilan, dan ide pada suatu masalah dalam bidang keahlian tertentu secara sistematis dan logis [2]. Beberapa penelitian telah dilakukan untuk rekomendasi topik tugas akhir dengan pengelompokkan K-Means Clustering, misal penelitian yang menunjukkan bahwa nilai mata kuliah wajib berpengaruh dengan penentuan topik tugas akhir mahasiswa [1]. Penelitian lain memberikan berdasarkan kemiripan transkrip akademik masukan dari rekomendasi tanpa pengelompokkan dan menerapkan pengguna yaitu mahasiswa yang sedang mencari ide temu kembali informasi [6]. Transkrip mahasiswa tersebut akan sebelumnya, pada penelitian ini terjadi pengelompokkan dibandingkan dengan transkrip akademik mahasiswa dan temu kembali tugas akhir sebagai rekomendasi terdahulu. Pada sistem rekomendasi yang diusulkan dilakukan kuliah (MK) dalam transkrip akademik mahasiswa serta ekstraksi topik dari hasil pengelompokkan dengan data tugas akhir yaitu judul dan abstrak. Kemungkinan data transkrip yang mirip dan tersedia dalam dataset dengan data pengguna, sehingga untuk mengurangi kandidat judul tugas akhir maka dilakukan pengklasteran/ pengelompokkan. Ukuran representasi vektor tersebut yang berupa vektor kolom dan bukan vektor baris sama dengan jumlah kata indeks, sedemikian hingga pengurangan kata melalui proses stemming dan stopword removal akan mengurangi dimensi vektor
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
